摘要
针对航空受限空间火灾探测高误报的问题,在现有技术成果基础上对多种火灾探测方式进行研讨,并提出1种基于BP神经网络技术的飞机机身内部受限空间火灾联合探测报警方法。该方法结合现有烟雾感应、气体传感器探测等常用火灾探测技术,以红外热成像探测为辅助手段,采用神经网络实现数据融合,对模拟实验舱火灾烟雾进行联合探测,在单一火灾探测方式基础上提高了探测准确率。
Aiming at the problem of high false alarms in the fire detection of aviation confined space,various fire detection methods were discussed based on the existing technical achievements,and a joint detection and alarm method of fire in the confined space inside the aircraft fuselage based on the BP neural network technology was proposed.The method combined the existing smoke sensing technology,gas sensor detection and other common fire detection technologies,and used the infrared thermal imaging detection as an auxiliary means.The neural network was utilized to realize the data fusion,and the joint detection was carried out on the fire smoke in the simulated experimental cabin.The detection accuracy was improved on the basis of single fire detection mode.
作者
邓力
刘全义
胡林
贺元骅
DENG Li;LIU Quanyi;HU Lin;HE Yuanhua(College of Civil Aviation Safety Engineering,Civil Aviation Flight University of China,Guanghan Sichuan 618307,China;Nanjing University of Science and Technology,Nanjing Jiangsu 210094,China)
出处
《中国安全生产科学技术》
CAS
CSCD
北大核心
2020年第1期158-162,共5页
Journal of Safety Science and Technology
基金
国家重点研发计划项目(2018YFC0809503)
国家自然科学基金项目(U1633203)
关键词
火灾探测
受限空间
神经网络
联合探测
fire detection
confined space
neural network
joint detection
